Launched Claude Opus 4.6, our most intelligent model for complex agentic tasks and long-horizon work. Opus 4.6 recommends adaptive thinking (thinking: {type: "adaptive"}); manual thinking (type: "enabled" with budget_tokens) is deprecated. Opus 4.6 does not support prefilling assistant messages.
The effort parameter is now generally available (no beta header required) and supports Claude Opus 4.6.
Launched the compaction API in beta, providing server-side context summarization for effectively infinite conversations.
Introduced data residency controls, allowing you to specify where model inference runs with the inference_geo parameter. US-only inference available at 1.1x pricing.
The 1M token context window is now available in beta for Claude Opus 4.6. Long context pricing applies to requests exceeding 200k input tokens.
Fine-grained tool streaming is now generally available on all models and platforms (no beta header required). The output_format parameter for structured outputs has been moved to output_config.format.
Fetched April 10, 2026